Triple
T19863142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dike |
E477320
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Themis |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Themis | Statement: [Dike, parent, Themis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Themis Context triple: [Dike, parent, Themis]
-
A.
Themis
chosen
Themis is the Greek Titaness and goddess of divine law, order, and prophetic wisdom, often associated with oracular sites such as Delphi.
-
B.
Erinys
Erinys is an epithet of the Greek goddess Demeter emphasizing her wrathful, vengeful aspect, particularly in myths involving the abduction of her daughter Persephone.
-
C.
Eunomia
Eunomia is the Greek goddess personifying good order, lawful governance, and social harmony.
-
D.
Hera
Hera is the queen of the Olympian gods in Greek mythology, revered as the goddess of marriage, women, and family.
-
E.
Artémis
Artémis is the French holding company of the Pinault family, overseeing a diverse portfolio of luxury, wine, art, and investment assets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6589c4c0081908cd51ff75441e7ac |
completed | April 20, 2026, 4:47 p.m. |
Created at: April 10, 2026, 1:51 p.m.